0063GitHub
jev-e2e
The same eBay test flow: 47 s on Jev, 79 s on Claude Sonnet 5.
Jason Lu’s jev-e2e writes end-to-end tests in plain English and runs them with Jev and Playwright. On the same eBay flow he reports completed-run medians of 47 seconds and $0.0067 for Jev, against 62 seconds and $0.0277 for GPT-5.6 Luna and 79 seconds and $0.4062 for Claude Sonnet 5.
perixtar/jev-e2eREADME ↗
# jev-e2e **Test your website in plain English. Get evidence for every result.** [](TEST_RESULTS.md) [](https://nodejs.org/) [](LICENSE) [Quick start](#quick-start) · [Write a test](#write-a-test) · [Benchmarks](#live-ebay-benchmark) · [CLI reference](docs/USAGE.md) · [Contribute](CONTRIBUTING.md) </div> Describe a flow and what should be true at the end. jev-e2e turns it into a test plan, uses Jev to select controls on the page, and runs the test with Playwright. Each result is **PASS**, **FAIL**, or **BLOCKED**, with an HTML report, JSON, and masked screenshots. **Local alpha:** CLI and browser workbench for Chromium websites. Install from source; an npm release is not yet available. ## Watch the eBay comparison Search and filter products → add two items → change quantity → remove an item → refresh and verify the cart. Three models, the same written steps, and 31 independent checks. The video shows actual browser recordings at **10.77× playback**. https://github.com/user-attachments/assets/3f6eea28-9f85-4d9c-9a76-ba90311ff673 [Download the 10-second video](docs/assets/ebay-benchmark.mp4) · [All nine attempts and methodology](docs/benchmarks/ebay-2026-09-18.md) This is a UI execution experiment with a shared human-authored plan and an extended benchmark observer. It does not measure natural-language planning or the unmodified CLI's reliability on eBay. ## Why jev-e2e? - **Write cases in plain English.** Use an optional planner for prose, or explicit `Goal`, `Step`, and `Expect` templates without it. - **Check the outcome.** Playwright verifies expectations independently. Missing evidence or unsupported requirements produce BLOCKED. - **See what happened.** Reports include expected and observed values, actions, timing, provider usage, and screenshots. - **R